ANALYSIS OF CONTENT-BASED IMAGE RETRIEVAL (CBIR) AND DECISION TREE METHODS FOR IDENTIFICATION TYPES OF COFFEE SEEDS

Rizki Saidah Srg Marahasian (Departement of Computer Science, Faculty of Science and Technology State Islamic University of North Sumatera Medan)
Muhammad Ikhsan (Departement of Computer Science, Faculty of Science and Technology State Islamic University of North Sumatera Medan)
Mhd Furqan (Departement of Computer Science, Faculty of Science and Technology State Islamic University of North Sumatera Medan)

INFOKUM
Vol. 10 No. 4 (2022): October, computer, information and engineering

Identification of the type oficoffee by nakedleye is difficult to distinguish so that special skills are needed, one method that can be usedlto identifylthe typeiof coffee is to use digital image processing such as Content Based ImageiRetrieval (CBIR) which aims to identify the characteristics or features of the object. This method is usedito carry out the feature identification process, onelof which is the texture feature possessed byiseveral types oflcoffee. By using the Decision Tree classification method, it aims to break down the decision-making process from complicated or complex to simpler so that it can be easier to make decisions. The concept used by the decision tree is to convert the data into a decision treeiand decision rules (rules). The texture feature extraction used is by using first-order parameters, the total dataset used is 50 images in 6 types of Arabica coffee. With the CBIR and Decision Tree systems, it is ablelto identifyithe type of coffee beans. Keywords: Content Based Image Retrieval (CBIR), Decision Tree, first orders parameters, Coffee Beans.